# Token Math: feedback on the headline, dek, and opening

## The strongest idea

**The CEO sits at the top of the spending chart and thinks everyone else is underspending.** That flips the usual rule about company spending, and it's the most surprising thing in the piece. The rest of the draft supplies the other half: **spend freely, then account for it.** Arielle asks three questions (what did it cost, what did it buy, what did we learn). Randy's 4.5-billion-token failure became a benchmark. Marcus matches each task to the right model. The package should promise both halves: permission to spend big, and the discipline of showing your work. Right now the hed and dek promise neither.

## Headline

**"Token Math"** is a label, not a claim. It also promises something the piece doesn't deliver. The draft never runs the math: there are no dollar figures or cost-per-result numbers, and Dan and Willie explicitly agree to "only then do the token math." If Token Math is a recurring column name, keep it as a kicker above the headline. It shouldn't be the headline itself.

**"How Many Tokens are Too Many?"** is a generic question, and the piece doesn't answer it. The argument isn't about a threshold. It's about whether the spending taught you something. (Title-case note: "Are" should be capitalized.)

**Suggested replacements (first choice first):**

1. **Our CEO Thinks We're Not Spending Enough on AI**. This is the surprising claim, stated plainly, and it fits an email subject line. The body supplies the qualifiers.
2. **Spend More Tokens. Then Show Your Work.** This covers both halves of the piece, and it works well if you'd rather center the accountability system than Dan.
3. **What 4.5 Billion Tokens Bought Us** is the most vivid option. But it points to Randy's section, not the opening, so you'd need to restructure the lede to use it.

Avoid a headline that starts with "Every CEO…". In a subject line it reads as "all CEOs."

## Dek

**"What's the ROI on experimentation?"** is a second question stacked on the headline. It doesn't add a detail or an implication. Like "Token Math," "ROI" promises a calculation the piece doesn't make.

**The alt dek, "When expensive experimentation is worth it and when to rein your tokenmaxxing in,"** contradicts the body, which says outright that "the goal isn't tokenmaxxing." It also overpromises clear rules: Arielle evaluates runs "case by case." And "rein your tokenmaxxing in" is clunky.

**Suggested replacement (pairs with hed #1):**

> Big token bills are fine—as long as you can say what they bought. Here's how Every decides when an expensive AI experiment pays off, including one that burned through 4.5 billion tokens.

**Shorter alternative:**

> Dan Shipper wants the team experimenting harder with AI. The catch: Every big run has to answer what it cost, what it bought, and what we learned.

## Opening paragraph

What works: the three-times gap is a great fact, and "whether the rest of us are being ambitious enough" is the right note to end on before you pivot to "The goal isn't tokenmaxxing."

Problems:

1. **The first sentence is the weakest one.** "Often if you are … you might think about…" hedges twice, uses a generic "you," and is missing a comma after "company." The paragraph builds up to its best fact instead of starting with it.
2. **It makes the same point twice with different levels of certainty.** Sentence two says Dan *thinks* everyone should "consider ramping up." Sentence four says the gap has him *wondering whether* people are ambitious enough. Keep one. The "wondering whether" version is more accurate and makes the better closer.
3. **It drops a factual qualifier.** The leaderboard is specifically *OpenAI* token usage (per the caption), but the lede says only "tokens." Say "OpenAI tokens" so the "more than three times" claim stays exact.
4. **The pronouns shift.** It moves from "you" to "the rest of us." Since this is an Inside Every piece, commit to "us."
5. **"Every CEO Dan Shipper"** is fine mid-sentence, but "Every's CEO, Dan Shipper" or "Dan Shipper, Every's CEO" avoids a stumble on "every CEO."

**Suggested replacement (keeps all the qualifiers):**

> Most people who find themselves at the top of their company's spending chart take it as a cue to cut back. Dan Shipper, Every's CEO, took it as a cue to look at everyone else. He uses more than three times as many OpenAI tokens as the next-highest user at the company, and the size of that gap has him wondering whether the rest of us are being ambitious enough with AI.

**Tighter alternative that leads with the fact:**

> Dan Shipper uses more than three times as many OpenAI tokens as anyone else at Every. Most people would see that as a reason to rein themselves in. Dan sees it as a reason to wonder whether the rest of us are being ambitious enough with AI.

Either version flows directly from hed #1 and sets up paragraph two ("The goal isn't tokenmaxxing…") without changes.

## Recommended package

- **HED:** Our CEO Thinks We're Not Spending Enough on AI
- **DEK:** Big token bills are fine—as long as you can say what they bought. Here's how Every decides when an expensive AI experiment pays off, including one that burned through 4.5 billion tokens.
- **LEDE:** the first suggested replacement above.

*Assumption: I treated "Token Math" as a possible recurring column name. If it isn't one, drop it entirely.*